{"total":24,"rows":[{"id":"2401.04343","title":"Private Fine-tuning of Large Language Models with Zeroth-order Optimization","created":"2024-01-09","cited_by_count":41,"area":null},{"id":"2410.18965","title":"On the Crucial Role of Initialization for Matrix Factorization","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2402.07818","title":"Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning","created":"2024-02-12","cited_by_count":14,"area":null},{"id":"2410.10074","title":"Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2408.10691","title":"Fine-Tuning and Deploying Large Language Models Over Edges: Issues and Approaches","created":"2024-08-20","cited_by_count":6,"area":null},{"id":"2502.03604","title":"Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training","created":"2025-02-05","cited_by_count":5,"area":null},{"id":"2402.18905","title":"Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2604.21905","title":"Low-Rank Adaptation Redux for Large Models","created":"2026-04-23","cited_by_count":3,"area":null},{"id":"2506.15588","title":"Memory-Efficient Differentially Private Training with Gradient Random Projection","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2511.10859","title":"Private Zeroth-Order Optimization with Public Data","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2602.02498","title":"Test-Time Detoxification without Training or Learning Anything","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2410.18114","title":"Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2502.20565","title":"Communication-Efficient and Differentially Private Vertical Federated Learning with Zeroth-Order Optimization","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2510.07304","title":"Cocoon: A System Architecture for Differentially Private Training with Correlated Noises","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2605.15622","title":"Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2506.00158","title":"Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2507.05610","title":"On the Inherent Privacy of Zeroth Order Projected Gradient Descent","created":"2025-07-08","cited_by_count":0,"area":null},{"id":"2510.16157","title":"Zeroth-Order Sharpness-Aware Learning with Exponential Tilting","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2511.02757","title":"ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2604.14669","title":"Zeroth-Order Optimization at the Edge of Stability","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.23180","title":"Self-Improving In-Context Learning","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.28760","title":"Inference-Native Zeroth-Order Optimization for LLMs","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2608.26655","title":"When Privacy Hurts Mergeability: Geometry-Aware Model Merging under Differential Privacy","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.29446","title":"SPADE-DFL: Communication-Efficient Decentralized Federated Learning via Derivative-Free Linearized ADMM","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}